爬取即刻的收藏

由於平時會收藏一些小黃圖，可是即刻的登陸機制對我比較費勁，好不容易找到網上的一片文章，可是看起來也比較費勁，大概知道怎麼回事了之後，本身擼了一套web

即刻的機制是這樣的，用戶掃碼進入網站，而後會獲得一個access_token，幾分鐘後會獲得一個refresh_token，而後之後再登陸的時候會調用一個接口，把refresh_token發給後臺獲得刷新的新的access_token。而第一個refresh_token須要去瀏覽器裏複製出來。代碼以下：json

#將傳入的refresh_token發給後臺去獲取
def refresh_token(refresh_token):
    user_agent = getUserAgent()#構造一個user_agent
    url = "https://app.jike.ruguoapp.com/app_auth_tokens.refresh"
    headers = {"Origin":"https://web.okjike.com",
               "Referer":"https://web.okjike.com/collection",
               "User-Agent":user_agent}
    headers["x-jike-refresh-token"] = str(refresh_token)
    r = requests.get(url,headers= headers)
    # print(r.text)
    content = r.text
    return content
複製代碼

構造user_agent st是我本身的工具類瀏覽器

from tools import Tools as tl
from tools import Settings as st

def getUserAgent():
    agentList = st.user_agent_list
    random_num = random.randint(1,len(agentList))
    user_agent = agentList[random_num-1]
    return user_agent
複製代碼

拿到最新的token以後就能夠想幹嗎幹嗎了bash

if __name__ == '__main__':      
    access_token =  refresh_token('eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJkYXRhIjoibjV0dVlqcVMrV0VVSDJKYTMwY0JYOTNcL1p4RTlqRExGTW1PZGRXcU9iaWZqOEZ3M3RrNjNNXC81enJsTUQ5ajNVMFVJRHZSNjlzYmhOWTBDejlQTXdXalwvSzBUcHRpRXJFMFZnXC9NSFVOYjFHaDVGajFzSEVKWm42TzR5aUk3XC9IaklrUENNeHNsSXRmNm1nVWdTUGZBbG1jZkNkdUdsblwvTGRvVGQ1UFJjQ3FNPSIsInYiOjMsIml2IjoiTWFQdTlpRUJqbUVcLzlIZURGdVVhZUE9PSIsImlhdCI6MTU1MzQwNzgwMS43NDl9.jWG-7-dUjZqSrgMJVnj1pIf52tqoSMHav_mop0_aABI')
    dic =  json.loads(access_token)
    startSpider('https://app.jike.ruguoapp.com/1.0/users/collections/list',dic['x-jike-access-token'])
複製代碼

爬蟲跑起來！app

loadMoreKey = None#這個全局變量是用來跑分頁的，即刻的分頁須要傳這個

def startSpider(url,access_token):
    user_agent = getUserAgent()
    headers = {"Accept":"application/json",
    "App-Version":"5.3.0",
    "Content-Type":"application/json",
    "Origin":"https://web.okjike.com",
    "platform":"web",
    "Referer":"https://web.okjike.com/collection",
    "User-Agent":user_agent}
    headers["x-jike-access-token"] = access_token
    tl.UsingHeaders = headers#這個是用來保存請求頭的，用來在下載的時候保持請求頭一致，能夠去掉
    data = {'limit':20,'loadMoreKey':loadMoreKey}

    response = requests.post(url,headers= headers, data= json.dumps(data))
    response.enconding = "ascii"
    print(response.status_code)
    data = json.loads(response.content.decode("utf-8"))
    global loadMoreKey
    loadMoreKey = data['loadMoreKey']
    data_list = data['data']
    for dic in data_list:
        pictures = dic['pictures']
        for picDic in pictures:
            picurl = picDic['picUrl']
            tl.downLoadFile(picurl)
    print('------結束20記錄------')
    startSpider(url,access_token)
複製代碼